Anonymization: The imperfect science of using data while preserving privacy

A Gadotti, L Rocher, F Houssiau, AM Creţu… - Science …, 2024 - science.org
Information about us, our actions, and our preferences is created at scale through surveys or
scientific studies or as a result of our interaction with digital devices such as smartphones …

Reconstructing training data with informed adversaries

B Balle, G Cherubin, J Hayes - 2022 IEEE Symposium on …, 2022 - ieeexplore.ieee.org
Given access to a machine learning model, can an adversary reconstruct the model's
training data? This work studies this question from the lens of a powerful informed adversary …

Sok: differential privacies

D Desfontaines, B Pejó - arXiv preprint arXiv:1906.01337, 2019 - arxiv.org
Shortly after it was first introduced in 2006, differential privacy became the flagship data
privacy definition. Since then, numerous variants and extensions were proposed to adapt it …

Real-world trajectory sharing with local differential privacy

T Cunningham, G Cormode… - arXiv preprint arXiv …, 2021 - arxiv.org
Sharing trajectories is beneficial for many real-world applications, such as managing
disease spread through contact tracing and tailoring public services to a population's travel …

Total variation distance privacy: Accurately measuring inference attacks and improving utility

J Jia, C Tan, Z Liu, X Li, Z Liu, S Lv, C Dong - Information Sciences, 2023 - Elsevier
Differential privacy (DP) is a general approach to defend against inference attacks, but hard
to balance the privacy-utility trade-off for some complex data analysis tasks. To improve the …

Learning numeric optimal differentially private truncated additive mechanisms

DM Sommer, L Abfalterer, S Zingg… - arXiv preprint arXiv …, 2021 - arxiv.org
Differentially private (DP) mechanisms face the challenge of providing accurate results while
protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP …

On the Choice of Databases in Differential Privacy Composition

V Hartmann, V Bindschaedler, R West - arXiv preprint arXiv:2209.13697, 2022 - arxiv.org
Differential privacy (DP) is a widely applied paradigm for releasing data while maintaining
user privacy. Its success is to a large part due to its composition property that guarantees …

Lowering the cost of anonymization

D Desfontaines - 2020 - research-collection.ethz.ch
The objective of this thesis is to make it easier to understand, use, and deploy strong
anonymization practices. We make progress towards this goal in three ways. First, we make …

Fighting Uphill Battles: Improvements in Personal Data Privacy

DM Sommer - 2021 - research-collection.ethz.ch
With the rise of modern information technology and the Internet, the worldwide
interconnectivity is resulting in a massive collection and evaluation of potentially sensitive …

Background Knowledge (B)

B Pejó, D Desfontaines - Guide to Differential Privacy Modifications: A …, 2022 - Springer
Background Knowledge (B) | SpringerLink Skip to main content Advertisement SpringerLink
Account Menu Find a journal Publish with us Track your research Search Cart Book cover …